CN117579080B - Medical care remote monitoring system based on 5G communication - Google Patents
Medical care remote monitoring system based on 5G communication Download PDFInfo
- Publication number
- CN117579080B CN117579080B CN202410076679.6A CN202410076679A CN117579080B CN 117579080 B CN117579080 B CN 117579080B CN 202410076679 A CN202410076679 A CN 202410076679A CN 117579080 B CN117579080 B CN 117579080B
- Authority
- CN
- China
- Prior art keywords
- character
- medical care
- care data
- sequence
- distance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 28
- 238000004891 communication Methods 0.000 title claims abstract description 16
- 238000005215 recombination Methods 0.000 claims abstract description 54
- 230000006798 recombination Effects 0.000 claims abstract description 54
- 230000008521 reorganization Effects 0.000 claims abstract description 14
- 230000000474 nursing effect Effects 0.000 claims abstract description 5
- 239000003550 marker Substances 0.000 claims description 50
- 238000000034 method Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 8
- 229940079593 drug Drugs 0.000 claims description 8
- 239000003814 drug Substances 0.000 claims description 8
- 230000036772 blood pressure Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 3
- 239000008280 blood Substances 0.000 claims description 3
- 210000004369 blood Anatomy 0.000 claims description 3
- 230000036760 body temperature Effects 0.000 claims description 3
- 229910052760 oxygen Inorganic materials 0.000 claims description 3
- 239000001301 oxygen Substances 0.000 claims description 3
- 230000036387 respiratory rate Effects 0.000 claims description 3
- 238000001647 drug administration Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 5
- 238000001514 detection method Methods 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 26
- 238000007906 compression Methods 0.000 description 12
- 230000006835 compression Effects 0.000 description 12
- 230000000694 effects Effects 0.000 description 11
- 238000006243 chemical reaction Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 3
- 238000013144 data compression Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
- H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
- H03M7/70—Type of the data to be coded, other than image and sound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to the field of data processing, in particular to a medical care remote monitoring system based on 5G communication, which comprises: the medical care data acquisition module, the data layering module, the data reorganization module and the remote monitoring module acquire the target degree of each type of character distance sequence by counting the distance between each type of characters in medical care data, and weight corresponding to the target degree of the mark character distance sequence and each distance value frequency is obtained according to the target degree of the mark character distance sequence; acquiring optimal layering step length by using the weight, and acquiring a plurality of data character subsequences; according to the recombination degree between subsequences; acquiring a reorganization priority and acquiring a reorganized data sequence; compressing the recombined data by using Huffman coding to obtain compressed data; the data are recombined, so that more data are stored in a limited storage space, and the patient nursing condition is obtained by carrying out anomaly detection on the compressed data, thereby achieving the purpose of remote monitoring and simultaneously enabling the monitoring result to be more accurate.
Description
Technical Field
The invention relates to the field of data processing, in particular to a medical care remote monitoring system based on 5G communication.
Background
The medical care data comprises a large amount of multi-mode data such as text information, physiological signals and the like, the storage requirement of the data is huge, the medical care data is often required to be stored for a long time, the condition of a patient needs to be referred to according to historical data, and the rehabilitation state of the patient is judged according to the change condition of the historical data, so that the large amount of medical care data is required to be stored, and the purpose of remote monitoring is achieved.
The traditional data compression and storage usually adopts Huffman coding to compress medical care data according to the occurrence frequency of characters, the medical care data is subjected to coding conversion according to the occurrence frequency of the characters in the medical care data by counting the occurrence frequency of the characters, so that the aim of data compression is achieved, but Huffman coding usually aims at single character coding conversion, a large amount of similar data or repeated data exist in the medical care data, and when single characters are adopted for coding conversion, the occurrence frequency of the large number of characters is similar, so that the compression effect is greatly influenced.
Disclosure of Invention
In order to solve the above problems, the present invention provides a medical care remote monitoring system based on 5G communication, the system comprising:
the medical care data acquisition module acquires medical care data, wherein the medical care data comprises body temperature, heart rate, blood pressure, respiratory rate, blood oxygen saturation, a drug treatment scheme, drug dosage, drug administration time and a care record, and the medical care data comprises a plurality of characters of different types;
the data layering module acquires a distance sequence of each type of character according to the distance between adjacent characters in the same type of characters; obtaining the target degree of each type of character distance sequence according to the distribution of the distance values in each type of character distance sequence; screening a plurality of mark character distance sequences from all the character distance sequences according to the target degree;
acquiring the weight corresponding to the frequency of each distance value in each marker character distance sequence according to the target degree of the marker character distance sequence and the length of the marker character distance sequence;
acquiring the preference degree of each distance value according to the weight value corresponding to each distance value frequency in the distance sequence of all the marking characters; obtaining optimal layering step length according to the preference degree of each distance value Layering the medical care data sequence by utilizing the optimal layering step length to obtain a plurality of medical care data character subsequences;
the data reorganization module is used for acquiring a first basic medical care data character subsequence, and acquiring the reorganization degree of each medical care data character subsequence and the first basic medical care data character subsequence according to the matching degree of the character combination in each medical care data character subsequence and the first basic medical care data character subsequence; acquiring an alternative recombined medical care data character subsequence according to the recombination degree of each medical care data character subsequence and the first standard medical care data character subsequence, recombining the alternative recombined medical care data character subsequence and the first standard medical care data character subsequence, acquiring the priority of all standard medical care data character subsequences, acquiring the recombined medical care data sequence according to the priority, and acquiring a phrase according to the occurrence frequency of character combinations in the recombined medical care data;
and the remote monitoring module is used for carrying out compression storage on the recombined medical care data sequence, obtaining the nursing condition of the patient by decompressing the compressed data, and carrying out remote monitoring on the medical care according to the nursing condition.
Preferably, the obtaining the target degree of each type of character distance sequence according to the distribution of the distance values in each type of character distance sequence includes the steps of:
obtaining a frequency sequence according to the distance frequency of all characters under the b character type; the maximum value of the frequency sequence of the b-th character type is recorded asRemove->In addition, the mean value of all distance frequencies in the frequency sequence is obtained and is recorded as +.>The method comprises the steps of carrying out a first treatment on the surface of the The specific calculation formula of the target degree of each type of character distance sequence is as follows:
in the middle ofIndicate->Class character distance sequence target degree.
Preferably, the step of obtaining the weight corresponding to the frequency of each distance value in each marker character distance sequence according to the target degree of the marker character distance sequence and the length of the marker character distance sequence includes the following steps:
the calculation method of the weight corresponding to the frequency of each distance value in each marker character distance sequence comprises the following steps:
in the middle ofIndicate->Weight corresponding to the frequency of each distance value in the distance sequence of the individual marker characters, +.>Indicate->The target degree of the distance sequence of the individual marker characters is obtained +.>Characters corresponding to the distance sequence of the individual marker characters, < >>Indicating that the class character is at->Number of occurrences in the sequence of medical care data, +. >Indicate->The number of characters of the type with the largest number of characters in the medical care data sequence; wherein->There are multiple distance values in the distance sequence of the marker characters, count +.>The frequency of each distance value in the distance sequence of the marker characters>The weight value of the frequency of each distance value in the distance sequence of the individual marker characters is +.>。
Preferably, the obtaining the preference degree of each distance value according to the weight value corresponding to each distance value frequency in the distance sequence of all the marker characters includes the steps of:
the method for acquiring the preference degree of each distance value comprises the following steps:
in the middle ofIndicating a distance value of +.>Is (are) preferred degree of->Indicate->The>Distance value>Representing the number of marker character distance sequences in the medical care data sequence,/->Indicate->The distance value in the distance sequence of the individual marker characters is +.>Frequency of occurrence, ++>Indicate->The distance value in the distance sequence of the individual marker characters is +.>Is a weight of (2).
Preferably, the layering processing of the medical care data sequence by using the optimal layering step length to obtain a plurality of medical care data character subsequences includes the steps of:
selecting one character every L characters from the first character in the medical care data sequence, forming a character sub-sequence by the selected characters, and starting from the second character in the medical care data sequence every L characters And selecting one character from the characters, forming a character subsequence by a plurality of selected characters, and the like until the iteration is stopped after all the characters in the medical care data sequence are selected, so as to obtain a plurality of medical care data character subsequences.
Preferably, the step of obtaining the recombination degree of each medical care data character sub-sequence and the first reference medical care data character sub-sequence according to the matching degree of the character combination in each medical care data character sub-sequence and the first reference medical care data character sub-sequence includes the steps of:
counting the occurrence frequency of each character in each medical care data character subsequence, and selecting a medical care data character subsequence corresponding to the character frequency with the largest occurrence frequency as a first standard medical care data character subsequence;
the specific calculation formula of the recombination degree is as follows:
in the middle ofIndicate->Degree of recombination of the medical care data character sub-sequence with the first reference medical care data character sub-sequence,/->Indicate->Frequency of phrase with highest occurrence number after combination of medical care data character subsequence and first standard medical care data character subsequence, +. >Indicate>Phrase frequency average of all phrases except.
Preferably, the step of acquiring the priorities of all the character sub-sequences of the reference medical care data includes the steps of:
presetting a recombination degree threshold, acquiring a medical care data character subsequence with the recombination degree larger than the preset recombination degree threshold and the largest recombination degree from all medical care data character subsequences, and recording the medical care data character subsequence as an alternative recombination medical care data character subsequenceThe method comprises the steps of carrying out a first treatment on the surface of the Will->The characters at the same position in the first basic medical care data character subsequence are spliced end to obtain a second basic medical care data character subsequence, and +.>Deleting;
acquiring a medical care data character subsequence with the recombination degree larger than a preset recombination degree threshold and the maximum recombination degree from the rest medical care data character subsequences, and marking the medical care data character subsequence as an alternative recombination medical care data character subsequenceThe method comprises the steps of carrying out a first treatment on the surface of the Will->Performing head-to-tail splicing on the characters at the same position in the second basic medical care data character subsequence to obtain a third basic medical care data character subsequence; will->Deleting; and the like, until the medical care data character subsequence with the recombination degree larger than the preset recombination degree threshold value does not exist in the rest medical care data character subsequences; obtaining a plurality of character subsequences of reference medical care data; all the reference medical care data character subsequences are respectively marked as a first priority and a second priority … … L-th priority according to the generation order.
Preferably, the step of acquiring the recombined medical care data sequence according to the priority includes the steps of:
the recombination process is as follows: placing a first character of a first priority medical care data character sub-sequence in a first position in the medical care data sequence, placing a first character of a second priority medical care data character sub-sequence in a second position in the medical care data sequence, placing a first character of a third priority medical care data character sub-sequence in a third position in the medical care data sequence, andthe first character in the subsequence of prioritized medical care data characters is placed at +.>A location at which reorganization of a first character in all of the medical care data character sub-sequences is completed; similarly, the second character in the sub-sequence of characters of the first priority medical care data is placed in the medical care data sequence +.>A position in which a second character of the sub-sequence of characters of the medical care data of the second priority is placed in the medical care data sequence +.>A position, a second character in the sub-sequence of medical care data characters of a third priority is placed in the medical care data sequence +. >Position, th->The second character in the subsequence of prioritized medical care data characters is placed at +.>A position, at which time the reorganization of the second character in all medical care data character sub-sequences is completed; and similarly, finishing the recombination of all the characters in all the medical care data character subsequences.
Preferably, the step of obtaining the phrase according to the occurrence frequency of the character combination in the recombined medical care data includes the following steps:
each term in the basic medical care data character subsequence is recorded as a phrase, the occurrence frequency of all phrases is counted, the occurrence frequency of the corresponding phrases is larger than the frequency average value of all single characters in the phrase in the medical care data sequence, the corresponding phrases are recorded as a whole, and the corresponding phrases are recorded as basic phrases, so that a plurality of basic phrases are obtained.
Preferably, the step of obtaining the distance sequence of each type of character according to the distance between adjacent characters in the same type of character includes the following steps:
collecting the first collectedThe medical care data sequence is subjected to character type statistics, and the first part is in accordance with the characters>The sequence of the medical care data sequences is respectively marked as a first type character, a second type character, a third type character and a first +. >Class character and->Class character, wherein->The total number of the character types of the medical care data sequence is +.>According to the character of each class at +.>And acquiring the distance sequence of each type of character according to the sequence of the medical care data sequence and the distance between adjacent characters in the same type of character.
The invention has the following beneficial effects:
the method comprises the steps of obtaining the periodicity degree of each type of character through the distance between adjacent characters of each type of character, obtaining the optimal splitting step length according to the periodicity degree of each type of character, splitting a medical care data sequence by utilizing the optimal splitting step length, enabling the distribution of characters in partial medical care data character subsequences to be redundant as far as possible and to be in periodic distribution, recombining and merging the medical care data character subsequences according to the similarity among the medical care data character subsequences, enabling a large number of repeated phrases to appear in merged data, obtaining the optimal phrase type through counting the frequency of the repeated characters, carrying out frequency counting on the phrases and single characters through Huffman coding, carrying out character conversion, greatly improving the compression effect, guaranteeing that more data are stored in a limited storage space, enabling medical care analysis results to be more accurate, and further guaranteeing that medical care remote monitoring achieves the effect of real time and accuracy.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a system block diagram of a medical care remote monitoring system based on 5G communication according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of the specific implementation, structure, characteristics and effects of the medical care remote monitoring system based on 5G communication according to the invention with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the medical care remote monitoring system based on 5G communication provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a medical care remote monitoring system based on 5G communication according to an embodiment of the present invention is shown, and the system includes the following modules:
the medical care data acquisition module 101 is used for acquiring medical care data.
Medical care data are acquired by manually inputting, scanning paper care records, importing other system data and the like, wherein the medical care data comprise medical care related information such as body temperature, heart rate, blood pressure, respiratory rate, blood oxygen saturation, drug treatment scheme, drug dosage, administration time, care records and the like, so as to obtain a medical care data sequence, different types of data are acquired separately when the medical care data sequence is acquired, namely the same type of data are put together to form the same type of medical care data sequence, and the medical care data sequence is recorded as a first data sequenceSequences of medical care data, how many types of medical care data are, +. >The value of (a) is how large, in this embodiment, the blood pressure data is taken as an example, and other types of data are also taken as the first medical care data sequence. The medical care data sequence contains a plurality of character types, including special symbols such as numbers, chinese characters, letters, punctuation marks and the like.
It should be noted that: since the characters of the medical care data sequence may be repeated in large numbers, such as with blood pressure values or with certain drug names, the other data may be repeated in large numbers. For repeated characters to be compressed to save storage space when being stored, the existing compression algorithm, such as huffman coding, compresses the medical care data sequence by utilizing the probability of the characters, the existing huffman coding only depends on the frequency of single characters when utilizing huffman tree for coding conversion, and the embodiment also needs to consider the distribution of the characters in the medical care data sequence, and combine the characters according to the distribution to form character combination, so the embodiment combines the distribution characteristics of the characters in the medical care data sequence to split and periodically analyze the medical care data sequence to ensure that better compression effect can be obtained in the existing compression algorithm.
The data layering module 102 is configured to obtain a subsequence of different characters of the medical care data.
It should be noted that: when the Huffman coding is used for constructing the Huffman tree for coding conversion, the more characters with the same frequency in the Huffman tree, the worse the compression effect is when coding compression is carried out, so that the characters need to be combined, and the number of the characters with the same frequency is reduced. But the number of character combinations or the number of character types is enhanced, so that the character combinations are formed by combining the characters which have similar occurrence frequency and are in paired occurrence, the number of the character types is increased as few as possible, the memory space occupied by the construction of the Huffman tree is reduced, the medical care data sequence is subjected to layering processing in a self-adaptive manner, and the layered data is recombined, so that the character combinations which are in paired occurrence are as many as possible, the frequency distribution of the characters is in an extremely uneven state, and the compression effect of the medical care data is greatly improved.
Collecting the first collectedThe medical care data sequence is subjected to character type statistics, and the first part is in accordance with the characters>The sequence of the medical care data sequences is respectively marked as the 1 st type character, the 2 nd type character, the 3 rd type character, the … … and the +. >Class character, … …, ->Class character, wherein->Medical care data sequenceThe total number of character types is +.>According to the character of each class at +.>The sequence of the medical care data sequences is obtained according to the distance between adjacent characters in the same type of characters, wherein the +.>The medical care data sequence +.>The distance sequence of the class character is marked as +.>The expression form is as follows:wherein->Distance value representing the i-th character of the b-th character,/or->Equal to +.f. in the b-th character type>The first character and->The distance between the characters, in this embodiment the distance between the characters refers to the difference in the sequence numbers of the characters in the sequence of medical care data, wherein +.>The medical care data sequence +.>The number of class characters is。
Obtaining the target degree of each type of character distance sequence according to the distribution of distance values in each type of character distance sequence, establishing a statistical histogram, and counting each type of character distance sequenceMiddle distance value->The frequency of occurrence of the (b) character is recorded as the distance frequency of the (i) character in the (b) character type, the distance frequency of all the (b) character types form a frequency sequence of the (b) character type, and the maximum value of the frequency sequence of the (b) character type is recorded as- >Remove->In addition, the mean value of all distance frequencies in the frequency sequence is obtained and is recorded as +.>The method comprises the steps of carrying out a first treatment on the surface of the The specific calculation formula of the target degree of each type of character distance sequence is as follows:
in the middle ofIndicate->Class character distance sequence target degree, +.>And->The larger the difference, the more distance sequence is specified>The similarity of each distance value is large, i.e. distance sequence +.>There are a number of identical distance values, at this point the description of the firstThe character distribution in the class character exhibits a strong periodicity +.>The greater the degree of targeting of the class character distance sequence. At this time get +.>The medical care data sequence +.>The target degree of the character distance sequence is obtained in a similar way.
Acquiring the optimal layering step length of each medical care data sequence according to the target degree of each type of character distance sequence in each medical care data sequence, and setting a character distance sequence target degree threshold valueIn this embodiment->For example, other values may be set for implementation; by means of the character distance sequence target degree threshold +.>Screening the character distance sequence, if +.>The target degree of the character-like distance sequence is more than or equal to the target degree threshold value of the character distance sequence >Will be->The class character distance sequence is marked as a marker character distance sequence, and all marker character distance sequences are obtained.
The present embodiment continues with the first embodimentThe medical care data sequence was analyzed:
the number of the distance sequence of the marker characters is recorded asThe method for calculating the weight corresponding to the frequency of each distance value in each marker character distance sequence comprises the following steps of:
in the middle ofIndicate->Weight corresponding to the frequency of each distance value in the distance sequence of the individual marker characters, +.>Indicate->The target degree of the distance sequence of the individual marker characters is obtained +.>Characters corresponding to the distance sequence of the individual marker characters, < >>Indicating that the class character is at->Number of occurrences in the sequence of medical care data, +.>Indicate->The number of characters of the type with the largest number of characters in the medical care data sequence; wherein->There are multiple distance values in the distance sequence of the marker characters, count +.>The frequency of each distance value in the distance sequence of the marker characters>The weight value of the frequency of each distance value in the distance sequence of the individual marker characters is +. >The method comprises the steps of carrying out a first treatment on the surface of the First->The longer and the +.>The greater the target degree of the sequence of marker characters from, the description +.>The number of characters of the marking characters is large and +.>The distribution of the individual marker characters more closely approximates to a periodic distribution, so +.>The greater the weight corresponding to the frequency of each distance value in the distance sequence of each marker character, the weight corresponding to the frequency of each distance value in the distance sequence of all marker characters is obtained in the same way.
Acquiring the preference degree of each distance value according to the weight value corresponding to each distance value frequency in all the marking character distance sequences, taking the distance value with the largest preference degree as the optimal layering step length of each medical care data sequence, layering each medical care data sequence by utilizing the optimal layering step length of each medical care data sequence, and acquiring the preference degree of each distance value by the following steps:
in the middle ofIndicating a distance value of +.>Is (are) preferred degree of->Indicate->The>Distance value>Indicate->Number of marker character distance sequences in the medical care data sequence,/->Indicate->The distance value in the distance sequence of the individual marker characters is +.>Frequency of occurrence, ++>Indicate- >The distance value in the distance sequence of the individual marker characters is +.>Weights of (2); calculating the maximum value +.>Preferably maximum>The corresponding distance value is marked +.>Maximum value of degree of preference +.>The corresponding distance value is marked +.>As->And (3) carrying out layering processing on each medical care data sequence by utilizing the optimal layering step length.
The layering treatment comprises the following specific processes:
selecting a character from the first character in the medical care data sequence every L characters, wherein the selected characters form a character subsequence, and the characters in the character subsequence are respectively the first character, the L-th character, the 2L-th character, … and the L-th character in the medical care data sequenceThe sub-sequence is marked as a first medical care data character sub-sequence, and similarly, one character is selected from the second character in the medical care data sequence every L characters, and a plurality of selected characters form a character sub-sequence, wherein the characters in the character sub-sequence are respectively the second character, the L+1th character, the 2L+1th character, the … and the L-th character in the medical care data sequence>A character, marking the sub-sequence as a second medical care data character sub-sequence, and so on; from the +.o in the medical care data sequence >Beginning with a character, wherein->The value range of (2) is +.>Selecting +.f in the medical care data sequence>First->First->First, theUp to->The individual characters form->Medical care data character subsequence, thereby completing the +.>Layering of the medical care data sequence, resulting in +.>A sub-sequence of medical care data characters.
And the data reorganization module 103 is used for reorganizing the medical care data character subsequences with higher similarity.
It should be noted that: after layering treatment, obtainThe length of each medical care data character subsequence is similar, meanwhile, the distribution of characters in part of the medical care data character subsequences has strong periodicity, if the medical care data character subsequences with high similarity are recombined, the medical care data character subsequences are placed together to form character combinations, the redundancy degree of the character combinations is greatly increased, and the compression effect of the medical care data is greatly improved when the character combinations are regarded as a whole.
Counting the occurrence frequency of each character in each medical care data character subsequence, and marking as，/>Represent the firstMedical care data character subsequence +. >The occurrence frequency of the seed characters is that a medical care data character subsequence corresponding to the character frequency with the largest occurrence frequency is selected from all medical care data character subsequences as a first basic medical care data character subsequence, and the first basic medical care data character subsequence is obtained according to the matching degree of each medical care data character subsequence and the character combination in the first basic medical care data character subsequence>The degree of recombination of the medical care data character subsequence with the first reference medical care data character subsequence is first described +.>Combining the sub-sequence of medical care data characters with the characters at each position in the sub-sequence of first reference medical care data characters to form a character combination, i.e. the +.>Combining a first character in the sub-sequence of medical care data characters with a first character in the sub-sequence of first reference medical care data characters to form a first phrase, and adding->Combining a second character in the sub-sequence of medical care data characters with a second character in the sub-sequence of first reference medical care data characters to form a second phrase, and adding +.>The +.f. in the medical care data character subsequence>The first reference medical care data character sub-sequence is +. >The individual characters are combined to form +.>Phrase, thereby obtaining the mostThe word group is regarded as a whole, and the first +.>Medical care data character subsequence and first reference medical carePhrase frequencies of different phrases after the data character subsequences are combined, and the phrase with the maximum frequency is marked as +.>Will remove->The phrase frequency average value of all phrases except for the phrase is marked as +.>The method comprises the steps of carrying out a first treatment on the surface of the First->The specific calculation formula of the recombination degree of the medical care data character subsequence and the first reference medical care data character subsequence is as follows:
in the middle ofIndicate->Degree of recombination of the medical care data character sub-sequence with the first reference medical care data character sub-sequence,/->Indicate->Frequency of phrase with highest occurrence number after combination of medical care data character subsequence and first standard medical care data character subsequence, +.>Indicate>Phrase frequency average value of all phrases except the phrase; />And->The greater the difference, the description of +.>The medical care data character sub-sequence is more similar to the period of the characters in the first reference medical care data character sub-sequence, and +.>The medical care data character subsequence has larger occupation ratio of the same characters in the first standard medical care data character subsequence, the occupation ratio of the same phrase is also larger after the combination, and a large number of single characters can be recombined to form the same phrase after the recombination, namely the first phrase is represented >The degree of recombination of the medical care data character subsequence with the first reference medical care data character subsequence is large. And similarly, acquiring the recombination degree of each medical care data character subsequence and the first standard medical care data character subsequence.
Setting a threshold value of the recombination degreeIn this embodiment->For example, other values may be set for implementation; by threshold of degree of recombination->Screening each medical care data character subsequence, if +.>The recombination degree of the medical care data character subsequence is more than or equal to a threshold value of the recombination degree +.>Then do->Marking the medical care data character subsequence, and selecting all the sequences meeting the recombination degree threshold value +.>The medical care data character subsequence with the largest recombination degree value is selected as the candidate recombined medical care data character subsequence, and is recorded asWill->Reorganizing with a first reference medical care data character subsequence; at this time, the character subsequence of the reference medical care data is updated, will +.>The medical care data character subsequence recombined with the first standard medical care data character subsequence is used as a second standard medical care data character subsequence, at the moment, the characters in the second standard medical care data character subsequence are updated into phrases, the operation is continued, the judgment of the recombination degree of the rest medical care data character subsequence and the second standard medical care data character subsequence is continued until the recombination threshold requirement is not met, at the moment, a first phrase is obtained, the length of the phrase is the number of the recombined medical care data character subsequences, and for convenience of expression, the phrase after the recombination is recited according to the characters; at this time, the reference medical care data character subsequence is continuously searched for in the medical care data character subsequence which has not been judged yet, and is taken as the +. >And (3) continuously judging the recombination degree according to the standard medical care data character subsequence until all medical care data character subsequences are judged to be finished, and stopping according to the judgmentAnd (3) sequencing the priorities of all the medical care data character sub-sequences according to the sequence of the sequences, wherein the priority of the first basic medical care data character sub-sequence is highest, the first priority is taken as the first priority, the priority of the second basic medical care data character sub-sequence is taken as the second priority immediately after the first priority, and the priorities of all the medical care data character sub-sequences are acquired in the same way.
The medical care data sequences are recombined according to the priorities of all the medical care data character subsequences, and the recombination process is as follows: placing a first character of a first priority medical care data character sub-sequence in a first position in the medical care data sequence, placing a first character of a second priority medical care data character sub-sequence in a second position in the medical care data sequence, placing a first character of a third priority medical care data character sub-sequence in a third position in the medical care data sequence, andthe first character in the subsequence of prioritized medical care data characters is placed at +. >A location at which reorganization of a first character in all of the medical care data character sub-sequences is completed; similarly, the second character in the sub-sequence of characters of the first priority medical care data is placed in the medical care data sequence +.>A position in which a second character of the sub-sequence of characters of the medical care data of the second priority is placed in the medical care data sequence +.>A position, a second character in the sub-sequence of medical care data characters of a third priority is placed in the medical care data sequence +.>Position, th->The second character in the subsequence of prioritized medical care data characters is placed at +.>A position, at which time the reorganization of the second character in all medical care data character sub-sequences is completed; and similarly, finishing the recombination of all the characters in all the medical care data character subsequences to obtain the recombined medical care data sequence.
The remote monitoring module 104 is configured to remotely monitor a care state of a patient.
Each term in the basic medical care data character subsequence is marked as a phrase, the occurrence frequency of all phrases is counted, the occurrence frequency of the corresponding phrases is larger than the frequency average value of all single characters in the phrases in the medical care data sequence, the corresponding phrases are marked as a whole, and the whole is marked as basic phrases, so that a plurality of basic phrases are obtained.
And counting the frequencies of all single characters and phrases in the recombined medical care data sequence by using Huffman codes, constructing a Huffman tree by using the frequencies of the single characters and phrases, performing code conversion on the recombined medical care data sequence by using Huffman codes according to the Huffman tree, realizing the compression of the recombined medical care data sequence, and transmitting the compressed data and the sequence original sequence corresponding to the recombination priority of the medical care data character subsequence.
After receiving the corresponding compressed data, the remote end firstly decodes the data according to Huffman coding to obtain a recombined medical care data sequence, inversely transforms the recombined medical care data according to the original sequence of the sequence corresponding to the recombination priority of the medical care data character subsequence, and firstly splits the recombined medical care data sequence to obtainA sub-sequence of characters of the medical care data to be obtained +.>Rearranging the sub-sequences of the medical care data characters according to the original sequence, and combining to obtain an original medical care data sequence; on the remote monitoring platform, medical staff can process and analyze decompressed medical care data by using a data analysis tool; the method comprises trend analysis, abnormality detection and the like, wherein through setting proper thresholds and rules, when the data of a patient exceeds a set range or abnormal conditions occur, the remote monitoring platform can generate an alarm or prompt to inform medical staff in time; causing medical personnel to take corresponding actions and interventions including remote calls, video conferences, remote medication adjustments, etc.; medical personnel determine the condition of the patient based on the patient's medical care data and provide instructions or advice.
In summary, the system of the invention comprises a medical care data acquisition module, a data layering module, a data reorganization module and a remote monitoring module, the periodicity degree of each type of character is obtained through the distance between adjacent characters of each type of character, the optimal splitting step length is obtained according to the periodicity degree of each type of character, the medical care data sequence is split by utilizing the optimal splitting step length, the character distribution in partial medical care data character subsequences is redundant as far as possible and is periodically distributed, the medical care data character subsequences are reorganized and combined according to the similarity among the medical care data character subsequences, a large number of repeated phrases appear in the combined data, the frequency of the repeated characters is counted to obtain the optimal phrase type, the frequency of the phrases and the single characters is counted through Huffman coding, the compression effect is greatly improved, more data are stored in the limited storage space, the medical care analysis result is more accurate, and the medical care remote monitoring is ensured to achieve the real-time accurate effect.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (7)
1. Medical care remote monitoring system based on 5G communication, characterized in that, the system includes:
the medical care data acquisition module acquires medical care data, wherein the medical care data comprises body temperature, heart rate, blood pressure, respiratory rate, blood oxygen saturation, a drug treatment scheme, drug dosage, drug administration time and a care record, and the medical care data comprises a plurality of characters of different types;
the data layering module acquires a distance sequence of each type of character according to the distance between adjacent characters in the same type of characters; obtaining the target degree of each type of character distance sequence according to the distribution of the distance values in each type of character distance sequence; screening a plurality of mark character distance sequences from all the character distance sequences according to the target degree;
acquiring the weight corresponding to the frequency of each distance value in each marker character distance sequence according to the target degree of the marker character distance sequence and the length of the marker character distance sequence;
acquiring the preference degree of each distance value according to the weight value corresponding to each distance value frequency in the distance sequence of all the marking characters; obtaining optimal layering step length according to the preference degree of each distance valueLayering the medical care data sequence by utilizing the optimal layering step length to obtain a plurality of medical care data character subsequences;
The data reorganization module is used for acquiring a first basic medical care data character subsequence, and acquiring the reorganization degree of each medical care data character subsequence and the first basic medical care data character subsequence according to the matching degree of the character combination in each medical care data character subsequence and the first basic medical care data character subsequence; acquiring an alternative recombined medical care data character subsequence according to the recombination degree of each medical care data character subsequence and the first standard medical care data character subsequence, recombining the alternative recombined medical care data character subsequence and the first standard medical care data character subsequence, acquiring the priority of all standard medical care data character subsequences, acquiring the recombined medical care data sequence according to the priority, and acquiring a phrase according to the occurrence frequency of character combinations in the recombined medical care data;
the remote monitoring module compresses and stores the recombined medical care data sequence, acquires the nursing condition of the patient by decompressing the compressed data, and remotely monitors the medical care according to the nursing condition;
the method for obtaining the target degree of each type of character distance sequence according to the distribution of the distance values in each type of character distance sequence comprises the following steps:
Obtaining a frequency sequence according to the distance frequency of all characters under the b character type; the maximum value of the frequency sequence of the b-th character type is recorded asRemove->In addition, the mean value of all distance frequencies in the frequency sequence is obtained and is recorded as +.>The method comprises the steps of carrying out a first treatment on the surface of the The specific calculation formula of the target degree of each type of character distance sequence is as follows:
in the middle ofIndicate->The target degree of the character-like distance sequence;
the step of obtaining the preference degree of each distance value according to the weight value corresponding to each distance value frequency in the distance sequence of all the marking characters comprises the following steps:
the method for acquiring the preference degree of each distance value comprises the following steps:
in the middle ofIndicating a distance value of +.>Is (are) preferred degree of->Indicate->The>Distance value>Representing the number of marker character distance sequences in the medical care data sequence,/->Indicate->The distance value in the distance sequence of the individual marker characters is +.>Frequency of occurrence, ++>Indicate->The distance value in the distance sequence of the individual marker characters is +.>Weights of (2);
the method for acquiring the recombination degree of each medical care data character subsequence and the first standard medical care data character subsequence according to the matching degree of the character combination in each medical care data character subsequence and the first standard medical care data character subsequence comprises the following steps:
Counting the occurrence frequency of each character in each medical care data character subsequence, and selecting a medical care data character subsequence corresponding to the character frequency with the largest occurrence frequency as a first standard medical care data character subsequence;
the specific calculation formula of the recombination degree is as follows:
in the middle ofIndicate->Degree of recombination of the medical care data character sub-sequence with the first reference medical care data character sub-sequence,/->Indicate->Frequency of phrase with highest occurrence number after combination of medical care data character subsequence and first standard medical care data character subsequence, +.>Indicate>Phrase frequency average of all phrases except.
2. The 5G communication-based medical care remote monitoring system according to claim 1, wherein the step of obtaining the weight corresponding to the frequency of each distance value in each marker character distance sequence according to the target degree of the marker character distance sequence and the length of the marker character distance sequence comprises the steps of:
the calculation method of the weight corresponding to the frequency of each distance value in each marker character distance sequence comprises the following steps:
in the middle ofIndicate->Weight corresponding to the frequency of each distance value in the distance sequence of the individual marker characters, +. >Indicate->The target degree of the distance sequence of the individual marker characters is obtained +.>Characters corresponding to the distance sequence of the individual marker characters, < >>Indicating that the class character is at->Out of the medical care data sequenceThe number of cases>Indicate->The number of characters of the type with the largest number of characters in the medical care data sequence; wherein->There are multiple distance values in the distance sequence of the marker characters, count +.>The frequency of each distance value in the distance sequence of the marker characters>The weight value of the frequency of each distance value in the distance sequence of the individual marker characters is +.>。
3. The 5G communication based medical care remote monitoring system of claim 1, wherein the layering the medical care data sequence with the optimal layering step length to obtain a plurality of medical care data character subsequences comprises the steps of:
selecting one character every L characters from the first character in the medical care data sequence, forming a character sub-sequence by the selected characters, and starting from the second character in the medical care data sequence every L charactersSelecting one character from the characters, forming a character subsequence by a plurality of selected characters, and the like until iteration is stopped after all characters in the medical care data sequence are selected, so as to obtain a plurality of medical care data character subsequences 。
4. The 5G communication based medical care telemonitoring system according to claim 1, wherein said acquiring priorities of all reference medical care data character sub-sequences comprises the steps of:
presetting a recombination degree threshold, acquiring a medical care data character subsequence with the recombination degree larger than the preset recombination degree threshold and the largest recombination degree from all medical care data character subsequences, and recording the medical care data character subsequence as an alternative recombination medical care data character subsequenceThe method comprises the steps of carrying out a first treatment on the surface of the Will->The characters at the same position in the first basic medical care data character subsequence are spliced end to obtain a second basic medical care data character subsequence, and +.>Deleting;
acquiring a medical care data character subsequence with the recombination degree larger than a preset recombination degree threshold and the maximum recombination degree from the rest medical care data character subsequences, and marking the medical care data character subsequence as an alternative recombination medical care data character subsequenceThe method comprises the steps of carrying out a first treatment on the surface of the Will->Performing head-to-tail splicing on the characters at the same position in the second basic medical care data character subsequence to obtain a third basic medical care data character subsequence; will->Deleting; and the like, until no medical care with the recombination degree larger than the preset recombination degree threshold value exists in the residual medical care data character subsequence A subsequence of rational data characters; obtaining a plurality of character subsequences of reference medical care data; all the reference medical care data character subsequences are respectively marked as a first priority and a second priority … … L-th priority according to the generation order.
5. The 5G communication based medical care remote monitoring system of claim 1, wherein the acquiring the reorganized medical care data sequence according to the priority comprises the steps of:
the recombination process is as follows: placing a first character of a first priority medical care data character sub-sequence in a first position in the medical care data sequence, placing a first character of a second priority medical care data character sub-sequence in a second position in the medical care data sequence, placing a first character of a third priority medical care data character sub-sequence in a third position in the medical care data sequence, andthe first character in the subsequence of prioritized medical care data characters is placed at +.>A location at which reorganization of a first character in all of the medical care data character sub-sequences is completed; similarly, the second character in the sub-sequence of characters of the first priority medical care data is placed in the medical care data sequence +. >A position in which a second character of the sub-sequence of characters of the medical care data of the second priority is placed in the medical care data sequence +.>A position, a second character in the sub-sequence of medical care data characters of a third priority is placed in the medical care data sequence +.>Position, th->The second character in the subsequence of prioritized medical care data characters is placed at +.>A position, at which time the reorganization of the second character in all medical care data character sub-sequences is completed; and similarly, finishing the recombination of all the characters in all the medical care data character subsequences.
6. The 5G communication-based medical care remote monitoring system according to claim 1, wherein the step of obtaining the phrase according to the occurrence frequency of the character combination in the reorganized medical care data comprises the steps of:
each term in the basic medical care data character subsequence is recorded as a phrase, the occurrence frequency of all phrases is counted, the occurrence frequency of the corresponding phrases is larger than the frequency average value of all single characters in the phrase in the medical care data sequence, the corresponding phrases are recorded as a whole, and the corresponding phrases are recorded as basic phrases, so that a plurality of basic phrases are obtained.
7. The 5G communication based medical care remote monitoring system according to claim 1, wherein the step of obtaining the distance sequence of each type of character according to the distance between adjacent characters in the same type of character comprises the steps of:
collecting the first collectedThe medical care data sequence is subjected to character type statistics, and the first part is in accordance with the characters>The order of occurrence in the sequence of medical care data,respectively marked as a first type character, a second type character, a third type character and a +.>Class character and->Class character, wherein->The total number of the character types of the medical care data sequence is +.>According to the character of each class at +.>And acquiring the distance sequence of each type of character according to the sequence of the medical care data sequence and the distance between adjacent characters in the same type of character. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410076679.6A CN117579080B (en) | 2024-01-19 | 2024-01-19 | Medical care remote monitoring system based on 5G communication |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410076679.6A CN117579080B (en) | 2024-01-19 | 2024-01-19 | Medical care remote monitoring system based on 5G communication |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117579080A CN117579080A (en) | 2024-02-20 |
| CN117579080B true CN117579080B (en) | 2024-03-26 |
Family
ID=89884915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410076679.6A Active CN117579080B (en) | 2024-01-19 | 2024-01-19 | Medical care remote monitoring system based on 5G communication |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117579080B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117811589B (en) * | 2024-03-01 | 2024-05-10 | 广州润普网络科技有限公司 | Enterprise data compression method and system based on artificial intelligence |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116405574A (en) * | 2023-06-08 | 2023-07-07 | 中国人民解放军总医院第二医学中心 | Remote medical image optimization communication method and system |
| CN117195006A (en) * | 2023-11-06 | 2023-12-08 | 南通双和食品有限公司 | Veterinary drug residue data management system for chicken |
-
2024
- 2024-01-19 CN CN202410076679.6A patent/CN117579080B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116405574A (en) * | 2023-06-08 | 2023-07-07 | 中国人民解放军总医院第二医学中心 | Remote medical image optimization communication method and system |
| CN117195006A (en) * | 2023-11-06 | 2023-12-08 | 南通双和食品有限公司 | Veterinary drug residue data management system for chicken |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117579080A (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117579080B (en) | Medical care remote monitoring system based on 5G communication | |
| Çınar et al. | Classification of normal sinus rhythm, abnormal arrhythmia and congestive heart failure ECG signals using LSTM and hybrid CNN-SVM deep neural networks | |
| US20200250554A1 (en) | Method and storage medium for predicting the dosage based on human physiological parameters | |
| CN116153452B (en) | Medical electronic medical record storage system based on artificial intelligence | |
| CN111696660A (en) | Artificial intelligence-based patient grouping method, device, equipment and storage medium | |
| CN116013488B (en) | Intelligent security management system for medical records with self-adaptive data rearrangement function | |
| CN116153453B (en) | Intelligent ring information management method and system based on cloud edge cooperation | |
| CN108847274A (en) | A kind of vital sign data processing method and system based on cloud platform | |
| CN112245728B (en) | Respirator false positive alarm signal identification method and system based on integrated tree | |
| CN116961675A (en) | Intelligent processing method for medical care data | |
| CN108847280A (en) | The smart cloud medical treatment real-time management system of case-based reasioning | |
| CN116700630B (en) | Organic-inorganic compound fertilizer production data optimized storage method based on Internet of things | |
| CN111685748A (en) | Quantile-based blood pressure early warning method, quantile-based blood pressure early warning device, quantile-based blood pressure early warning equipment and storage medium | |
| CN116369933A (en) | Arrhythmia detection method based on lightweight convolutional neural network and transducer fusion | |
| CN115868941A (en) | Information management method for intelligent ring | |
| CN113470799B (en) | Intelligent editor of comprehensive quality supervision platform for hospitals | |
| CN117481628A (en) | Wearable multi-parameter noninvasive hemodynamic monitoring method and system | |
| CN115882867B (en) | Data compression storage method based on big data | |
| Mukhopadhyay et al. | A combined application of lossless and lossy compression in ECG processing and transmission via GSM-based SMS | |
| CN111797619B (en) | Device and method for automatically calculating observation items according to formulas | |
| CN114947801A (en) | Vital sign state identification method and system based on Transformer network | |
| CN111755022A (en) | Mixed auscultation signal separation method based on time sequence convolution network and related device | |
| TWI810901B (en) | Remote electrocardiogram monitoring device and electrocardiogram monitoring method | |
| CN117877686A (en) | Intelligent management method and system for traditional Chinese medicine nursing data | |
| CN118016225B (en) | Intelligent management method for electronic health record data after kidney transplantation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |